arXiv subjects

Yong Zhang

Publications and source records attributed to Yong Zhang.

At least 469 records · Page 26Linked to original sources

arXiv2021

ATOMS: ALMA Three-millimeter Observations of Massive Star-forming regions -- V. Hierarchical fragmentation and gas dynamics in IRDC G034.43+00.24

We present new 3-mm continuum and molecular lines observations from the ATOMS survey towards the massive protostellar clump, MM1, located in the filamentary infrared dark cloud (IRDC), G034.43+00.24 (G34). The lines observed are the tracers of either dense gas (e.g. HCO+/H13CO+ J = 1-0) or outflows (e.g. CS J = 2-1). The most complete picture to date of seven cores in MM1 is revealed by dust continuum emission. These cores are found to be gravitationally bound, with virial parameter, $α_{vir}<2$. At least four outflows are identified in MM1 with a total outflowing mass of $\sim 45 M_\odot$, and a total energy of $\sim 1\times 10^{47}$ erg, typical of outflows from a B0-type star. Evidence of hierarchical fragmentation, where turbulence dominates over thermal pressure, is observed at both the cloud and the clump scales. This could be linked to the scale-dependent, dynamical mass inflow/accretion on clump and core scales. We therefore suggest that the G34 cloud could be undergoing a dynamical mass inflow/accretion process linked to the multiscale fragmentation, which leads to the sequential formation of fragments of the initial cloud, clumps, and ultimately dense cores, the sites of star formation.

astro-ph.GA↗

arXiv2021

GasHisSDB: A New Gastric Histopathology Image Dataset for Computer Aided Diagnosis of Gastric Cancer

Background and Objective: Gastric cancer has turned out to be the fifth most common cancer globally, and early detection of gastric cancer is essential to save lives. Histopathological examination of gastric cancer is the gold standard for the diagnosis of gastric cancer. However, computer-aided diagnostic techniques are challenging to evaluate due to the scarcity of publicly available gastric histopathology image datasets. Methods: In this paper, a noble publicly available Gastric Histopathology Sub-size Image Database (GasHisSDB) is published to identify classifiers' performance. Specifically, two types of data are included: normal and abnormal, with a total of 245,196 tissue case images. In order to prove that the methods of different periods in the field of image classification have discrepancies on GasHisSDB, we select a variety of classifiers for evaluation. Seven classical machine learning classifiers, three Convolutional Neural Network classifiers, and a novel transformer-based classifier are selected for testing on image classification tasks. Results: This study performed extensive experiments using traditional machine learning and deep learning methods to prove that the methods of different periods have discrepancies on GasHisSDB. Traditional machine learning achieved the best accuracy rate of 86.08% and a minimum of just 41.12%. The best accuracy of deep learning reached 96.47% and the lowest was 86.21%. Accuracy rates vary significantly across classifiers. Conclusions: To the best of our knowledge, it is the first publicly available gastric cancer histopathology dataset containing a large number of images for weakly supervised learning. We believe that GasHisSDB can attract researchers to explore new algorithms for the automated diagnosis of gastric cancer, which can help physicians and patients in the clinical setting.

cs.CV↗

arXiv2021

Adaptive Multi-receptive Field Spatial-Temporal Graph Convolutional Network for Traffic Forecasting

Mobile network traffic forecasting is one of the key functions in daily network operation. A commercial mobile network is large, heterogeneous, complex and dynamic. These intrinsic features make mobile network traffic forecasting far from being solved even with recent advanced algorithms such as graph convolutional network-based prediction approaches and various attention mechanisms, which have been proved successful in vehicle traffic forecasting. In this paper, we cast the problem as a spatial-temporal sequence prediction task. We propose a novel deep learning network architecture, Adaptive Multi-receptive Field Spatial-Temporal Graph Convolutional Networks (AMF-STGCN), to model the traffic dynamics of mobile base stations. AMF-STGCN extends GCN by (1) jointly modeling the complex spatial-temporal dependencies in mobile networks, (2) applying attention mechanisms to capture various Receptive Fields of heterogeneous base stations, and (3) introducing an extra decoder based on a fully connected deep network to conquer the error propagation challenge with multi-step forecasting. Experiments on four real-world datasets from two different domains consistently show AMF-STGCN outperforms the state-of-the-art methods.

cs.LG↗

arXiv2021

EBJR: Energy-Based Joint Reasoning for Adaptive Inference

State-of-the-art deep learning models have achieved significant performance levels on various benchmarks. However, the excellent performance comes at a cost of inefficient computational cost. Light-weight architectures, on the other hand, achieve moderate accuracies, but at a much more desirable latency. This paper presents a new method of jointly using the large accurate models together with the small fast ones. To this end, we propose an Energy-Based Joint Reasoning (EBJR) framework that adaptively distributes the samples between shallow and deep models to achieve an accuracy close to the deep model, but latency close to the shallow one. Our method is applicable to out-of-the-box pre-trained models as it does not require an architecture change nor re-training. Moreover, it is easy to use and deploy, especially for cloud services. Through a comprehensive set of experiments on different down-stream tasks, we show that our method outperforms strong state-of-the-art approaches with a considerable margin. In addition, we propose specialized EBJR, an extension of our method where we create a smaller specialized side model that performs the target task only partially, but yields an even higher accuracy and faster inference. We verify the strengths of our methods with both theoretical and experimental evaluations.

cs.CV↗

arXiv2021

Repaint: Improving the Generalization of Down-Stream Visual Tasks by Generating Multiple Instances of Training Examples

Convolutional Neural Networks (CNNs) for visual tasks are believed to learn both the low-level textures and high-level object attributes, throughout the network depth. This paper further investigates the `texture bias' in CNNs. To this end, we regenerate multiple instances of training examples from each original image, through a process we call `repainting'. The repainted examples preserve the shape and structure of the regions and objects within the scenes, but diversify their texture and color. Our method can regenerate a same image at different daylight, season, or weather conditions, can have colorization or de-colorization effects, or even bring back some texture information from blacked-out areas. The in-place repaint allows us to further use these repainted examples for improving the generalization of CNNs. Through an extensive set of experiments, we demonstrate the usefulness of the repainted examples in training, for the tasks of image classification (ImageNet) and object detection (COCO), over several state-of-the-art network architectures at different capacities, and across different data availability regimes.

cs.CV↗

arXiv2021

Model Composition: Can Multiple Neural Networks Be Combined into a Single Network Using Only Unlabeled Data?

The diversity of deep learning applications, datasets, and neural network architectures necessitates a careful selection of the architecture and data that match best to a target application. As an attempt to mitigate this dilemma, this paper investigates the idea of combining multiple trained neural networks using unlabeled data. In addition, combining multiple models into one can speed up the inference, result in stronger, more capable models, and allows us to select efficient device-friendly target network architectures. To this end, the proposed method makes use of generation, filtering, and aggregation of reliable pseudo-labels collected from unlabeled data. Our method supports using an arbitrary number of input models with arbitrary architectures and categories. Extensive performance evaluations demonstrated that our method is very effective. For example, for the task of object detection and without using any ground-truth labels, an EfficientDet-D0 trained on Pascal-VOC and an EfficientDet-D1 trained on COCO, can be combined to a RetinaNet-ResNet50 model, with a similar mAP as the supervised training. If fine-tuned in a semi-supervised setting, the combined model achieves +18.6%, +12.6%, and +8.1% mAP improvements over supervised training with 1%, 5%, and 10% of labels.

cs.LG↗

arXiv2021

Gate-tunable Intrinsic Anomalous Hall Effect in Epitaxial MnBi2Te4 Films

Anomalous Hall effect (AHE) is an important transport signature revealing topological properties of magnetic materials and their spin textures. Recently, antiferromagnetic MnBi2Te4 has been demonstrated to be an intrinsic magnetic topological insulator that exhibits quantum AHE in exfoliated nanoflakes. However, its complicated AHE behaviors may offer an opportunity for the unexplored correlation between magnetism and band structure. Here, we show the Berry curvature dominated intrinsic AHE in wafer-scale MnBi2Te4 thin films. By utilizing a high-dielectric SrTiO3 as the back-gate, we unveil an ambipolar conduction and electron-hole carrier (n-p) transition in ~7 septuple layer MnBi2Te4. A quadratic relation between the saturated AHE resistance and longitudinal resistance suggests its intrinsic AHE mechanism. For ~3 septuple layer MnBi2Te4, however, the AHE reverses its sign from pristine negative to positive under the electric-gating. The first-principles calculations demonstrate that such behavior is due to the competing Berry curvature between polarized spin-minority-dominated surface states and spin-majority-dominated inner-bands. Our results shed light on the physical mechanism of the gate-tunable intrinsic AHE in MnBi2Te4 thin films and provide a feasible approach to engineering its AHE.

cond-mat.mtrl-sci↗

arXiv2021

Quantum Computation Using Action Variables

Recently, Lloyd and Montangero have made a brief research proposal on universal quantum computation in integrable systems. The main idea is to encode qubits into quantum action variables and build up quantum gates by the method of resonant control. We study this proposal to argue quantum computation using action variables as fault-tolerant quantum computation, whose fault-tolerance is guaranteed by the quantum KAM theorem. Besides, we view the Birkhoff norm form as a mathematical framework of the extended harmonic oscillator quantum computation.

quant-ph↗

arXiv2021

Robust Physical-World Attacks on Face Recognition

Face recognition has been greatly facilitated by the development of deep neural networks (DNNs) and has been widely applied to many safety-critical applications. However, recent studies have shown that DNNs are very vulnerable to adversarial examples, raising serious concerns on the security of real-world face recognition. In this work, we study sticker-based physical attacks on face recognition for better understanding its adversarial robustness. To this end, we first analyze in-depth the complicated physical-world conditions confronted by attacking face recognition, including the different variations of stickers, faces, and environmental conditions. Then, we propose a novel robust physical attack framework, dubbed PadvFace, to model these challenging variations specifically. Furthermore, considering the difference in attack complexity, we propose an efficient Curriculum Adversarial Attack (CAA) algorithm that gradually adapts adversarial stickers to environmental variations from easy to complex. Finally, we construct a standardized testing protocol to facilitate the fair evaluation of physical attacks on face recognition, and extensive experiments on both dodging and impersonation attacks demonstrate the superior performance of the proposed method.

cs.CV↗

arXiv2021

Large Magnetoresistance and Weak Antilocalization in V1-delta Sb2 Single Crystal

The binary pnictide semimetals have attracted considerable attention due to their fantastic physical properties that include topological effects, negative magnetoresistance, Weyl fermions and large non-saturation magnetoresistance. In this paper, we have successfully grown the high-quality V1-deltaSb2 single crystals by Sb flux method and investigated their electronic transport properties. A large positive magnetoresistance that reaches 477% under a magnetic field of 12 T at T = 1.8 K was observed. Notably, the magnetoresistance showed a cusp-like feature at the low magnetic fields and such feature weakened gradually as the temperature increased, which indicated the presence of weak antilocalization effect (WAL). The angle-dependent magnetoconductance and the ultra-large prefactor alpha extracted from the Hikami-Larkin-Nagaoka equation revealed that the WAL effect is a 3D bulk effect originated from the three-dimensional bulk spin-orbital coupling.

cond-mat.mtrl-sci↗

arXiv2021

Searching for an additional high-energy component in Fermi-LAT GRB afterglows

The VHE component from at least two GRBs, i.e., GRB180720B and GRB190114C, has been detected in the afterglow phase. We systematically analyzed 199 GRBs detected by Fermi-LAT during 2008-2019. If an additional high-energy component exists in the afterglows of Fermi-LAT GRBs, the best-fit spectral model could be a broken power-law (BPL) model with an upturn above a break energy. We compare the afterglow spectra using PL and BPL representations. Out of the 30 GRBs with >10GeV photons that arrived after T90, 25 GRBs are tentatively or significantly detected at 0.1-200 GeV after 2*T90. The spectrum of GRB131231A shows an upturn above a break of 1.6+-0.8~GeV, supporting the BPL model. For GRB131231A, we performed a modeling of its X-ray and gamma-ray spectra, and found that the SSC model can explain the upturn with acceptable parameter values. In the cases of GRBs 190114C, 171210A, 150902A, 130907A, 130427A, and 090902B, the improvement of the BPL fit compared to the PL fit is tentative or marginal. There is no conclusive evidence that an additional higher energy component commonly exists in Fermi-LAT GRB afterglows, except for a group of Fermi-LAT GRBs mentioned above. Such an additional high-energy component may be explained by the synchrotron self-Compton mechanism. Current and future VHE observations will provide important constraints on the issue.

astro-ph.HE↗

arXiv2021

Generating Self-Contained and Summary-Centric Question Answer Pairs via Differentiable Reward Imitation Learning

Motivated by suggested question generation in conversational news recommendation systems, we propose a model for generating question-answer pairs (QA pairs) with self-contained, summary-centric questions and length-constrained, article-summarizing answers. We begin by collecting a new dataset of news articles with questions as titles and pairing them with summaries of varying length. This dataset is used to learn a QA pair generation model producing summaries as answers that balance brevity with sufficiency jointly with their corresponding questions. We then reinforce the QA pair generation process with a differentiable reward function to mitigate exposure bias, a common problem in natural language generation. Both automatic metrics and human evaluation demonstrate these QA pairs successfully capture the central gists of the articles and achieve high answer accuracy.

cs.CL↗

arXiv2021

An Optimal Resource Allocator of Elastic Training for Deep Learning Jobs on Cloud

Cloud training platforms, such as Amazon Web Services and Huawei Cloud provide users with computational resources to train their deep learning jobs. Elastic training is a service embedded in cloud training platforms that dynamically scales up or down the resources allocated to a job. The core technique of an elastic training system is to best allocate limited resources among heterogeneous jobs in terms of shorter queueing delay and higher training efficiency. This paper presents an optimal resource allocator for elastic training system that leverages a mixed-integer programming (MIP) model to maximize the training progress of deep learning jobs. We take advantage of the real-world job data obtained from ModelArts, the deep learning training platform of Huawei Cloud and conduct simulation experiments to compare the optimal resource allocator with a greedy one as benchmark. Numerical results show that the proposed allocator can reduce queuing time by up to 32% and accelerate training efficiency by up to 24% relative to the greedy resource allocator, thereby greatly improving user experience with Huawei ModelArts and potentially enabling the realization of higher profits for the product. Also, the optimal resource allocator is fast in decision-making, taking merely 0.4 seconds on average.

eess.SY↗

arXiv2021

Morphological study of the nested planetary nebula Hubble 12

We present a visible-infrared imaging study of young planetary nebula (PN) Hubble 12 (Hb 12; PN G111.8-02.8) obtained with Hubble Space Telescope (HST) archival data and our own Canada-France-Hawaii Telescope (CFHT) measurements. Deep HST and CFHT observations of this nebula reveal three pairs of bipolar structures and an arc-shaped filament near the western waist of Hb 12. The existence of nested bipolar lobes together with the presence of H2 knots suggests that these structures originated from several mass-ejection events during the pre-PN phase. To understand the intrinsic structures of Hb 12, a three-dimensional model enabling the visualisation of this PN at various orientations was constructed. The modelling results show that Hb 12 may resemble other nested hourglass nebulae, such as Hen 2-320 and M 2-9, suggesting that this type of PN may be common and the morphologies of PNs are not so diverse as is shown by their visual appearances. The infrared spectra show that this PN has a mixed chemistry. We discuss the possible material that may cause the unidentified infrared emissions. The analyses of the infrared spectra and the spectral energy distribution suggest the existence of a cool companion in the nucleus of this object.

astro-ph.SR↗

arXiv2021

Auto-Split: A General Framework of Collaborative Edge-Cloud AI

In many industry scale applications, large and resource consuming machine learning models reside in powerful cloud servers. At the same time, large amounts of input data are collected at the edge of cloud. The inference results are also communicated to users or passed to downstream tasks at the edge. The edge often consists of a large number of low-power devices. It is a big challenge to design industry products to support sophisticated deep model deployment and conduct model inference in an efficient manner so that the model accuracy remains high and the end-to-end latency is kept low. This paper describes the techniques and engineering practice behind Auto-Split, an edge-cloud collaborative prototype of Huawei Cloud. This patented technology is already validated on selected applications, is on its way for broader systematic edge-cloud application integration, and is being made available for public use as an automated pipeline service for end-to-end cloud-edge collaborative intelligence deployment. To the best of our knowledge, there is no existing industry product that provides the capability of Deep Neural Network (DNN) splitting.

cs.LG↗

arXiv2021

DAE-GAN: Dynamic Aspect-aware GAN for Text-to-Image Synthesis

Text-to-image synthesis refers to generating an image from a given text description, the key goal of which lies in photo realism and semantic consistency. Previous methods usually generate an initial image with sentence embedding and then refine it with fine-grained word embedding. Despite the significant progress, the 'aspect' information (e.g., red eyes) contained in the text, referring to several words rather than a word that depicts 'a particular part or feature of something', is often ignored, which is highly helpful for synthesizing image details. How to make better utilization of aspect information in text-to-image synthesis still remains an unresolved challenge. To address this problem, in this paper, we propose a Dynamic Aspect-awarE GAN (DAE-GAN) that represents text information comprehensively from multiple granularities, including sentence-level, word-level, and aspect-level. Moreover, inspired by human learning behaviors, we develop a novel Aspect-aware Dynamic Re-drawer (ADR) for image refinement, in which an Attended Global Refinement (AGR) module and an Aspect-aware Local Refinement (ALR) module are alternately employed. AGR utilizes word-level embedding to globally enhance the previously generated image, while ALR dynamically employs aspect-level embedding to refine image details from a local perspective. Finally, a corresponding matching loss function is designed to ensure the text-image semantic consistency at different levels. Extensive experiments on two well-studied and publicly available datasets (i.e., CUB-200 and COCO) demonstrate the superiority and rationality of our method.

cs.CV↗

arXiv2021

The singularities for a periodic transport equation

In this paper, we consider a 1D periodic transport equation with nonlocal flux and fractional dissipation $$ u_{t}-(Hu)_{x}u_{x}+κΛ^αu=0,\quad (t,x)\in R^{+}\times S, $$ where $κ\geq0$, $0<α\leq1$ and $S=[-π,π]$. We first establish the local-in-time well-posedness for this transport equation in $H^{3}(S)$. In the case of $κ=0$, we deduce that the solution, starting from the smooth and odd initial data, will develop into singularity in finite time. If adding a weak dissipation term $κΛ^αu$, we also prove that the finite time blowup would occur.

math.AP↗

arXiv2021

Finding Representative Interpretations on Convolutional Neural Networks

Interpreting the decision logic behind effective deep convolutional neural networks (CNN) on images complements the success of deep learning models. However, the existing methods can only interpret some specific decision logic on individual or a small number of images. To facilitate human understandability and generalization ability, it is important to develop representative interpretations that interpret common decision logics of a CNN on a large group of similar images, which reveal the common semantics data contributes to many closely related predictions. In this paper, we develop a novel unsupervised approach to produce a highly representative interpretation for a large number of similar images. We formulate the problem of finding representative interpretations as a co-clustering problem, and convert it into a submodular cost submodular cover problem based on a sample of the linear decision boundaries of a CNN. We also present a visualization and similarity ranking method. Our extensive experiments demonstrate the excellent performance of our method.

cs.CV↗